© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 14540
    Prev
    Next
    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash

    the neuron detects numeric constants (especially hexadecimal-style 0x... tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sampler
    -0.07
     burgl
    -0.07
     Freel
    -0.07
     Obst
    -0.07
    Miami
    -0.07
     writings
    -0.07
     nederland
    -0.06
    //****************************************************************
    -0.06
    .coroutines
    -0.06
     Feet
    -0.06
    POSITIVE LOGITS
    x
    0.08
    (${
    0.07
    {x
    0.07
    X
    0.06
    foregroundColor
    0.06
    aska
    0.06
    onz
    0.06
     hasn
    0.06
    atan
    0.06
    xb
    0.06
    Activations Density 0.011%

    No Known Activations